Nightshift Labs Web Extract API is a paid API for AI agents from nightshift-x402.nightshift-labs.workers.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-11-19).
Fetches a public web page by URL and returns its content as cleaned Markdown, along with metadata like title, links, word count, and HTTP status.
Fetch any public web page and return clean Markdown of the main content plus title, meta description, word count and absolute links. Strips scripts, navigation and boilerplate. Good for feeding pages to an LLM.
A JSON object containing the page URL, HTTP status code, page title, full page content as cleaned Markdown (up to maxChars, default 20,000), an array of links found on the page, word count, and a truncated flag indicating whether the content was cut off.
GEThttps://nightshift-x402.nightshift-labs.workers.dev/v1/web/extract?utm_source=zero.xyzChoose this endpoint when an AI agent needs to read the content of a specific public web page and receive it in structured, readable Markdown format with metadata. It is a good fit for pay-per-call agent workflows using USDC on Base via the x402 protocol, particularly when you need page title, links, and word count alongside the text. Prefer alternatives if you need to crawl entire sites, handle authenticated pages, or require structured data extraction with field mapping.
| Field | Type | Description |
|---|---|---|
| inputrequired | object | |
| output | object |
{
"type": "json",
"example": {
"url": "https://example.com/",
"links": [],
"title": "Example Domain",
"status": 200,
"markdown": "# Example Domain\n\nThis domain is for use in…",
"truncated": false,
"wordCount": 30
}
}No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"